spaCy/spacy/tests/regression/test_issue4120.py

24 lines
843 B
Python
Raw Normal View History

2019-08-20 17:33:09 +03:00
from spacy.matcher import Matcher
from spacy.tokens import Doc
def test_issue4120(en_vocab):
"""Test that matches without a final {OP: ?} token are returned."""
matcher = Matcher(en_vocab)
matcher.add("TEST", [[{"ORTH": "a"}, {"OP": "?"}]])
2019-08-20 17:33:09 +03:00
doc1 = Doc(en_vocab, words=["a"])
assert len(matcher(doc1)) == 1 # works
2019-08-20 17:33:09 +03:00
doc2 = Doc(en_vocab, words=["a", "b", "c"])
assert len(matcher(doc2)) == 2 # fixed
2019-08-20 17:33:09 +03:00
matcher = Matcher(en_vocab)
matcher.add("TEST", [[{"ORTH": "a"}, {"OP": "?"}, {"ORTH": "b"}]])
2019-08-20 17:33:09 +03:00
doc3 = Doc(en_vocab, words=["a", "b", "b", "c"])
assert len(matcher(doc3)) == 2 # works
matcher = Matcher(en_vocab)
matcher.add("TEST", [[{"ORTH": "a"}, {"OP": "?"}, {"ORTH": "b", "OP": "?"}]])
2019-08-20 17:33:09 +03:00
doc4 = Doc(en_vocab, words=["a", "b", "b", "c"])
assert len(matcher(doc4)) == 3 # fixed